R Coding Workshop: 3rd Meeting

GIS & Geospatial Data Analysis (Fall 2025)

R Coding Workshop: 3rd Meeting

Outline for today

Install and load R Packages
Tidyverse: coding style and collection of packages
- Pipeline operator
- readr: Read and write data
- Tidy Data: prepared for data analysis (next week)
Exploratory Data Analysis:dplyr continued
ggplot: Data Visualization

Tidyverse

Tidyverse coding style and packages

library(tidyverse)

Read and write data

uni_df <- tibble::tribble(
  ~university, ~year, ~current_country, ~lat, ~lon, ~exist_today,
  "Paris", 1150, "France", 48.8566, 2.3522, TRUE,
  "Salerno", 1173,  "Italy", 40.7711, 14.7905, TRUE,
  "Reggio", 1188, "Italy", 44.6450, 10.9277, TRUE,
  "Oxford", 1190, "United Kingdom", 51.7520, -1.2576, TRUE,
  "Bologna", 1200, "Italy", 44.4989, 11.3275, TRUE
)
uni_df

university	year	current_country	lat	lon	exist_today
Paris	1150	France	48.8566	2.3522	TRUE
Salerno	1173	Italy	40.7711	14.7905	TRUE
Reggio	1188	Italy	44.6450	10.9277	TRUE
Oxford	1190	United Kingdom	51.7520	-1.2576	TRUE
Bologna	1200	Italy	44.4989	11.3275	TRUE

uni_fpath <- 'data/university-1200.csv'
uni_df |> write_csv(uni_fpath)

uni_df |> rm()

uni_df <- read_csv(uni_fpath)
uni_df |> class()

[1] "spec_tbl_df" "tbl_df"      "tbl"         "data.frame"

library(sf)
library(mapview)

uni_sf <- uni_df |> st_as_sf(coords = c('lon','lat'), crs = 4326)
uni_sf |> mapview(label = 'university')

uni_sf_fpath <- 'data/uni-1200-sf.gpkg'
# uni_sf |> st_write(uni_sf_fpath)

uni_sf |> rm()
uni_sf <- st_read(uni_sf_fpath)

Reading layer `uni-1200-sf' from data source 
  `/Users/toyuan/dohnanyi/data/uni-1200-sf.gpkg' using driver `GPKG'
Simple feature collection with 5 features and 4 fields
Geometry type: POINT
Dimension:     XY
Bounding box:  xmin: -1.2576 ymin: 40.7711 xmax: 14.7905 ymax: 51.752
Geodetic CRS:  WGS 84

uni_sf |> mapview(label = 'university')

`dplyr` for Exploratory Data Analysis

More functions from dplyr
Merits of pipeline operator |>

Tidyverse EDA

Import Data: Challenged Books from 2000 to 2010

source: American Library Society (America Library Association)

library(bayesrules)

book_challenge_df <- book_banning |> as_tibble()
book_challenge_df |> head()

title	book_id	author	date	year	removed	explicit	occult	language	lgbtq	violent	state	political_value_index	median_income	hs_grad_rate	college_grad_rate
House of the Spirits, The	927	Allende, Isabel	2005-04-01	2005	0	1	1	1	1	1	AK	-13.4	15707.5	8.738042	0.6762701
It’s Not the Stork!: A Book About Girls, Boys, Babies and Bodies	1024	Harris, Robie	2008-02-06	2008	1	0	0	0	0	0	AK	-13.4	15707.5	8.738042	0.6762701
King Stork	1087	Pyle, Howard	2008-10-02	2008	0	0	0	0	0	1	AK	-13.4	15707.5	8.738042	0.6762701
How They Met and Other Stories	936	Levithan, David	2008-10-05	2008	0	0	0	0	0	0	AK	-13.4	15707.5	8.738042	0.6762701
Ghost in the Shell	764	Masamune, Shirow	2008-10-02	2008	0	0	0	0	0	0	AK	-13.4	15707.5	8.738042	0.6762701
King Stork	1087	Pyle, Howard	2003-09-13	2003	0	0	0	0	0	1	AK	-13.4	15707.5	8.738042	0.6762701

Tidy Data and Data Cleaning (next week)

book_challenge_df |> summary()

    title              book_id       author               date           
 Length:931         143    : 17   Length:931         Min.   :2000-01-01  
 Class :character   868    : 12   Class :character   1st Qu.:2002-11-16  
 Mode  :character   1849   : 10   Mode  :character   Median :2006-02-10  
                    1025   :  9                      Mean   :2005-12-16  
                    1083   :  8                      3rd Qu.:2009-03-18  
                    399    :  7                      Max.   :2010-09-09  
                    (Other):868                      NA's   :11          
      year      removed explicit antifamily occult  language lgbtq   violent
 Min.   :2000   0:714   0:632    0:891      0:895   0:694    0:842   0:797  
 1st Qu.:2002   1:217   1:299    1: 40      1: 36   1:237    1: 89   1:134  
 Median :2006                                                               
 Mean   :2005                                                               
 3rd Qu.:2009                                                               
 Max.   :2010                                                               
 NA's   :11                                                                 
    state           political_value_index median_income    hs_grad_rate   
 Length:931         Min.   :-20.2000      Min.   :-8466   Min.   :-6.662  
 Class :character   1st Qu.: -1.8000      1st Qu.: 1274   1st Qu.: 1.038  
 Mode  :character   Median :  2.0000      Median : 4218   Median : 2.338  
                    Mean   :  0.0304      Mean   : 4530   Mean   : 2.833  
                    3rd Qu.:  4.0000      3rd Qu.: 9908   3rd Qu.: 5.538  
                    Max.   : 13.4000      Max.   :19936   Max.   : 8.738  
                                                                          
 college_grad_rate
 Min.   :-9.2237  
 1st Qu.:-2.0237  
 Median : 0.2763  
 Mean   : 0.6043  
 3rd Qu.: 2.5763  
 Max.   : 9.1763

book_challenge_df |> dim()

[1] 931  17

remove 11 books with missing values (require justification!)

book_challenge_df <- book_challenge_df |> drop_na()
book_challenge_df |> dim()

[1] 920  17

duplicated rows?

# book_challenge_df |> group_by(book_id) |> filter(n_distinct(title) > 1) |> arrange(book_id) |> tail()

# book_challenge_df |> distinct(book_id, title)

Dimension:

(row x column)
920 Observations: number of recorded book challenges
17 Variables:
- observation-level
  - title, author, date
- state-level variables
  - median_income, political_value_index

Summary statistics:

the data type and the value range of the dataset

book_challenge_df |> summary()

    title              book_id       author               date           
 Length:920         143    : 17   Length:920         Min.   :2000-01-01  
 Class :character   868    : 12   Class :character   1st Qu.:2002-11-16  
 Mode  :character   1849   : 10   Mode  :character   Median :2006-02-10  
                    1025   :  9                      Mean   :2005-12-16  
                    1083   :  8                      3rd Qu.:2009-03-18  
                    399    :  7                      Max.   :2010-09-09  
                    (Other):857                                          
      year      removed explicit antifamily occult  language lgbtq   violent
 Min.   :2000   0:706   0:628    0:880      0:884   0:686    0:832   0:788  
 1st Qu.:2002   1:214   1:292    1: 40      1: 36   1:234    1: 88   1:132  
 Median :2006                                                               
 Mean   :2005                                                               
 3rd Qu.:2009                                                               
 Max.   :2010                                                               
                                                                            
    state           political_value_index median_income    hs_grad_rate   
 Length:920         Min.   :-20.20000     Min.   :-8466   Min.   :-6.662  
 Class :character   1st Qu.: -2.12500     1st Qu.: 1274   1st Qu.: 1.038  
 Mode  :character   Median :  2.00000     Median : 4218   Median : 2.338  
                    Mean   :  0.01326     Mean   : 4522   Mean   : 2.808  
                    3rd Qu.:  4.00000     3rd Qu.: 9908   3rd Qu.: 5.538  
                    Max.   : 13.40000     Max.   :19936   Max.   : 8.738  
                                                                          
 college_grad_rate
 Min.   :-9.2237  
 1st Qu.:-1.7237  
 Median : 0.2763  
 Mean   : 0.6042  
 3rd Qu.: 2.5763  
 Max.   : 9.1763

`dplyr` functions: `mutate()`

mutate(): creating new variables (columns) from existing variables
case: typecasting

book_challenge_df <- book_challenge_df |>
  mutate(
    yr = year(date),
    month = month(date),
    day = day(date),
    week_day = wday(date, label = TRUE)
    )

all(book_challenge_df$year == as.numeric(book_challenge_df$yr))

[1] TRUE

# book_challenge_df <- book_challenge_df |> mutate(year = yr) |> select(-yr)

count()

book_challenge_df |> count(week_day)

week_day	n
Sun	119
Mon	182
Tue	95
Wed	132
Thu	148
Fri	155
Sat	89

`dplyr` functions: `group_by()`

group observations by like variable value, why?

nrow(book_challenge_df[book_challenge_df$removed == 1,]) / nrow(book_challenge_df)

[1] 0.2326087

`dplyr` functions: `group_by()`

subset, stratify

book_challenge_df |> group_by(year) |> summarize(
    total_count = n(),
    removed_count = sum(removed == 1),
    removed_pct = (removed_count / total_count) * 100
)

year	total_count	removed_count	removed_pct
2000	71	26	36.61972
2001	111	26	23.42342
2002	52	16	30.76923
2003	88	14	15.90909
2004	83	20	24.09639
2005	52	15	28.84615
2006	54	9	16.66667
2007	38	15	39.47368
2008	122	37	30.32787
2009	197	22	11.16751
2010	52	14	26.92308

# A tibble: 11 × 4
    year total_count removed_count removed_pct
   <dbl>       <int>         <int>       <dbl>
 1  2000          71            26        36.6
 2  2001         111            26        23.4
 3  2002          52            16        30.8
 4  2003          88            14        15.9
 5  2004          83            20        24.1
 6  2005          52            15        28.8
 7  2006          54             9        16.7
 8  2007          38            15        39.5
 9  2008         122            37        30.3
10  2009         197            22        11.2
11  2010          52            14        26.9

expressive pipeline that aligns with DS workflow!
Base R:

total_count <- as.vector(
    tapply(
        book_challenge_df$removed,
        book_challenge_df$year,
        length
        )
)
removed_count <- as.vector(
    tapply(
        book_challenge_df$removed == 1,
        book_challenge_df$year,
        sum
        )
)
year_summary <- data.frame(
    year = 2000:2010,
    total_count = total_count,
    removed_count = removed_count,
    removed_pct = (removed_count / total_count) * 100
)
year_summary

Group Data by Geounit

state_level_vars <- c(
    "state", "political_value_index",
    "median_income", "hs_grad_rate", "college_grad_rate"
    )
# book_challenge_df |> group_by(across(state_level_vars)) |> summarize(count = n())

state_summary <- book_challenge_df |>
  group_by_at(state_level_vars) |>
  summarize(count = n())

state_summary

state	political_value_index	median_income	hs_grad_rate	college_grad_rate	count
AK	-13.4	15707.5	8.7380421	0.6762701	9
AL	-13.2	-5054.0	-4.2619579	-5.0237299	10
AR	-8.8	-6258.5	-4.2619579	-7.3237299	5
AZ	-6.1	3490.5	1.4380421	-0.5237299	12
CA	7.4	10119.0	-2.7619579	2.5762701	50
CO	-0.2	10346.5	7.3380421	8.6762701	80
CT	7.1	16247.5	4.4380421	7.3762701	6
DE	7.0	9167.5	3.0380421	0.9762701	2
FL	-1.8	372.0	0.3380421	-1.7237299	26
GA	-6.8	2239.5	-0.9619579	0.2762701	13
IA	1.0	3921.5	6.5380421	-2.8237299	13
ID	-17.4	3194.0	5.1380421	-2.3237299	14
IL	7.7	6489.5	1.8380421	2.0762701	39
IN	-6.2	1086.5	2.5380421	-4.6237299	20
KS	-11.5	144.5	6.4380421	1.7762701	13
KY	-10.4	-5880.5	-5.4619579	-6.9237299	13
LA	-9.7	-5120.5	-4.7619579	-5.3237299	12
MA	11.7	14048.5	5.2380421	9.1762701	8
MD	8.5	19404.5	4.2380421	7.3762701	5
ME	5.5	1335.5	5.8380421	-1.1237299	3
MI	3.8	2966.0	3.8380421	-2.2237299	34
MN	2.3	15378.0	8.3380421	3.3762701	17
MO	-3.1	1279.5	1.7380421	-2.4237299	11
MS	-9.5	-8466.5	-6.6619579	-7.1237299	1
MT	-7.1	-6482.0	7.6380421	0.3762701	7
NC	-4.3	-310.0	-1.4619579	-1.5237299	20
ND	-10.4	-813.0	4.3380421	-2.0237299	6
NE	-13.5	4927.5	7.0380421	-0.3237299	2
NH	1.6	17303.0	7.8380421	4.6762701	7
NJ	4.4	19935.5	2.5380421	5.7762701	11
NM	2.4	-2401.5	-0.6619579	-0.5237299	3
NY	10.2	5007.5	-0.4619579	3.3762701	24
OH	-0.7	2469.0	3.4380421	-2.9237299	29
OK	-16.9	-3087.5	1.0380421	-3.7237299	23
OR	4.0	1274.5	5.5380421	1.0762701	118
PA	2.0	4218.0	2.3380421	-1.6237299	147
RI	11.2	8141.0	-1.5619579	1.5762701	3
SC	-7.8	-2191.5	-3.2619579	-3.6237299	15
SD	-8.9	785.0	5.0380421	-2.5237299	3
TN	-8.7	-2995.5	-3.6619579	-4.4237299	13
UT	-20.2	12735.5	8.1380421	2.0762701	1
VA	-1.7	11296.0	1.9380421	5.4762701	33
VT	13.4	8467.0	6.8380421	5.3762701	13
WA	5.0	9907.5	7.5380421	3.6762701	9
WI	2.4	4234.5	5.5380421	-1.6237299	10
WV	-7.9	-7290.0	-4.3619579	-9.2237299	3
WY	-19.7	4081.5	8.3380421	-2.1237299	4

# sanity check
state_summary |> dim() |> print()

[1] 47  6

state_summary$count |> sum()

[1] 920

Adding Spatial Dimension

library(sf)
library(mapview)
library(rnaturalearth)
library(viridis)

Prepare the Geometry

state_sf <- ne_states(country = 'United States of America') |> select(postal, gn_name, gadm_level, region)
state_sf |> dim() |> print()

[1] 51  5

state_sf |> mapview()

Combine by column value match

plot_sf <- state_sf |>
  left_join(
    state_summary,
    by = join_by(postal == state)
)
plot_sf |> head()

postal	gn_name	gadm_level	region	political_value_index	median_income	hs_grad_rate	college_grad_rate	count	geometry
WA	Washington	1	West	5.0	9907.5	7.538042	3.6762701	9	MULTIPOLYGON (((-122.753 48…
ID	Idaho	1	West	-17.4	3194.0	5.138042	-2.3237299	14	MULTIPOLYGON (((-117.0382 4…
MT	Montana	1	West	-7.1	-6482.0	7.638042	0.3762701	7	MULTIPOLYGON (((-116.0482 4…
ND	North Dakota	1	Midwest	-10.4	-813.0	4.338042	-2.0237299	6	MULTIPOLYGON (((-104.0476 4…
MN	Minnesota	1	Midwest	2.3	15378.0	8.338042	3.3762701	17	MULTIPOLYGON (((-97.22609 4…
MI	Michigan	1	Midwest	3.8	2966.0	3.838042	-2.2237299	34	MULTIPOLYGON (((-84.4913 46…

state_summary |> select(state, count) |> filter(state == 'WA')

political_value_index	median_income	hs_grad_rate	state	count
5	9907.5	7.538042	WA	9

Choropleth

plot_sf |> mapview(zcol = 'count', label = 'gn_name')

plot_sf |> filter(is.na(count))

postal	gn_name	gadm_level	region	political_value_index	median_income	hs_grad_rate	college_grad_rate	count	geometry
TX	Texas	1	South	NA	NA	NA	NA	NA	MULTIPOLYGON (((-103.3115 2…
DC	District of Columbia	1	South	NA	NA	NA	NA	NA	MULTIPOLYGON (((-77.02293 3…
HI	Hawaii	1	West	NA	NA	NA	NA	NA	MULTIPOLYGON (((-154.8996 1…
NV	Nevada	1	West	NA	NA	NA	NA	NA	MULTIPOLYGON (((-114.0425 4…

`ggplot` plot with more controls

plot_sf |> ggplot() + geom_sf(aes(fill = count), color = 'white', size = 0.01) + scale_fill_viridis() + theme_bw()

R Coding Workshop: 3rd Meeting

R Coding Workshop: 3rd Meeting

Outline for today

Tidyverse

Read and write data

dplyr for Exploratory Data Analysis

Tidyverse EDA

dplyr functions: mutate()

dplyr functions: group_by()

dplyr functions: group_by()

Group Data by Geounit

Adding Spatial Dimension

Choropleth

ggplot plot with more controls

`dplyr` for Exploratory Data Analysis

`dplyr` functions: `mutate()`

`dplyr` functions: `group_by()`

`dplyr` functions: `group_by()`

`ggplot` plot with more controls